Neural Japanese Zero Anaphora Resolution using Smoothed Large-scale Case Frames with Word Embedding
Neural Japanese Zero Anaphora Resolution using Smoothed Large-scale Case Frames with Word Embedding
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Souta Yamashiro;Hitoshi Nishikawa;T. Tokunaga
中科院分区：
文献类型：
--
作者：
Souta Yamashiro;Hitoshi Nishikawa;T. Tokunaga
本文提出了一个日语零回指分解模型，该模型可以同时处理句内零回指和句间零回指。解决句间回指需要考虑大量句子边界之外的先行词候选者，这是训练模型和解决回指的关键障碍。为了解决这一问题，我们提出了一种有效的基于案例框架信息的候选剪枝方法。此外，我们还引入了一个局部单注意力RNN用于句子间回指解析，允许模型考虑与目标谓词的远程上下文。我们用日语平衡语料库评估了所提出的模型，并通过显示0.056点的准确性提高来证实候选修剪的有效性。
This paper presents a Japanese zero anaphora resolution model which deals with both intra-and inter-sentential zero anaphora. Solving inter-sentential anaphora needs to consider a large number of antecedent candidates beyond the sentence boundaries, which is a crucial obstacle for training the model and resolving the anaphora. To cope with this problem, we pro-pose an effective candidate pruning method using case frame information. Also, we introduce a local single-attention RNN for inter-sentential anaphora resolution, allowing the model to consider the distant context from the target predicate. We evaluated the proposed models with a Japanese balanced corpus and confirmed the effectiveness of the candidate pruning by showing 0.056 point increase of accuracy.